Application Research Of Neural Network Expert System To Fault Diagnosis Of Condenser

The thermodynamic characteristic of condensing system has a heavy impaction on the security and economy of a running turbine.It is important that establishing the monitoring and optimization model for fault diagnosis and improving the operation level.In this paper,condensing system's performance is discussed,and condensing system's common faults are analyzed and the cause and signs of condenser's vacuum falling are emphasized.The basic theory and system structure of Artificial Neural Network and Expert System are introduced in this paper.It designs a new method which combines the Experts System with the Artificial Neural Network to make application for fault diagnosis field better. Combined with each situation in detail,condenser diagnosis Expert System based on BP Neural Network is constructed.Trains Network,and then deals with diagnosis datum through making use of the learned Network,so it obtains diagnosis situation in detail.With MATLAB,making use of the Neural Network learning rules,the knowledge construction is completed;With DELPHI 7.0,fault diagnosis application software for the condensing system was developed.